Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2259 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9272. Min Range: -3.9272
Max Act: 3.9272. Min Act: -0.1700
Data Index: 4495702 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9272. Min Range: -3.9272
Max Act: 3.9272. Min Act: -0.1700
Data Index: 4511858 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9272. Min Range: -3.9272
Max Act: 3.8647. Min Act: -0.1700
Data Index: 5906394 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9272. Min Range: -3.9272
Max Act: 3.8647. Min Act: -0.1700
Data Index: 2147936 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9272. Min Range: -3.9272
Max Act: 3.8647. Min Act: -0.1700
Data Index: 6964375 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9272. Min Range: -3.9272
Max Act: 3.8334. Min Act: -0.1700
Data Index: 6144114 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9272. Min Range: -3.9272
Max Act: 3.8647. Min Act: -0.1700
Data Index: 4527202 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9272. Min Range: -3.9272
Max Act: 3.8334. Min Act: -0.1700
Data Index: 4937944 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9272. Min Range: -3.9272
Max Act: 3.8647. Min Act: -0.1700
Data Index: 2821151 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9272. Min Range: -3.9272
Max Act: 3.8334. Min Act: -0.1700
Data Index: 7799027 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9272. Min Range: -3.9272
Max Act: 3.8334. Min Act: -0.1700
Data Index: 686375 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9272. Min Range: -3.9272
Max Act: 3.8334. Min Act: -0.1700
Data Index: 2999648 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9272. Min Range: -3.9272
Max Act: 3.8334. Min Act: -0.1700
Data Index: 5980093 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9272. Min Range: -3.9272
Max Act: 3.8022. Min Act: -0.1700
Data Index: 2928116 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9272. Min Range: -3.9272
Max Act: 3.8334. Min Act: -0.1700
Data Index: 5427794 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9272. Min Range: -3.9272
Max Act: 3.8022. Min Act: -0.1700
Data Index: 3586132 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9272. Min Range: -3.9272
Max Act: 3.8022. Min Act: -0.1700
Data Index: 826759 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9272. Min Range: -3.9272
Max Act: 3.8022. Min Act: -0.1700
Data Index: 4254918 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9272. Min Range: -3.9272
Max Act: 3.8022. Min Act: -0.1700
Data Index: 5738212 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9272. Min Range: -3.9272
Max Act: 3.8022. Min Act: -0.1700
Data Index: 3060573 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19